Skip to content

Releases: HKUDS/LightRAG

v1.4.14

12 Apr 20:43
@danielaskdd danielaskdd
v1.4.14
5a2694e

Choose a tag to compare

View all tags
v1.4.14 Latest
Latest

What's New

  • feat(setup): support Atlas Local Docker for Mongo vector storage by @danielaskdd in #2925
  • perf: batch graph operations in ainsert_custom_kg for large-scale imports by @nszhsl in #2910
  • examples: add AG2 multi-agent demo with LightRAG retrieval by @faridun-ag2 in #2867

What's Fixed

  • fix: remove redundant file_path_placeholder lookup in _merge_edges_then_upsert by @jwchmodx in #2877
  • chore: remove dead config.ini / configparser code by @jwchmodx in #2887
  • chore: remove dead OLLAMA_NUM_CTX / args.ollama_num_ctx assignment by @jwchmodx in #2888
  • fix(webui): resolve all bun run lint errors in lightrag_webui by @danielaskdd in #2891
  • chore(webui): migrate ESLint stylistic plugin by @danielaskdd in #2893
  • docs(readme): restructure documentation and consolidate core api by @danielaskdd in #2896
  • fix pipeline status history trimming by @danielaskdd in #2897
  • fix: Corrected exception handling for LLM API timeouts where the subclass incorrectly passes keyword args by @hillct in #2902
  • Improve LLM API failure diagnostics by @danielaskdd in #2903
  • docs: deprecate config.ini in documentation by @danielaskdd in #2905
  • fix(auth): prevent JWT algorithm confusion attack (GHSA-8ffj-4hx4-9pgf) by @danielaskdd in #2907
  • fix(api): add missing metadata field in /query/data error response by @lawrence3699 in #2923
  • fix(utils): prevent remove_think_tags from truncating responses with embedded tags by @sjhddh in #2900
  • fix(opensearch): ensure consistent by lazy index refresh and real-time edge lookups by @danielaskdd in #2926
  • fix(kg): correct omission of isolated nodes in get_knowledge_graph during full graph retrieval by @danielaskdd in #2928

New Contributors

Full Changelog: v1.4.13...v1.4.14

Contributors

hillct, nszhsl, and 5 other contributors
Assets 2
Loading

v1.4.13

02 Apr 17:00
@danielaskdd danielaskdd
v1.4.13
f096487

Choose a tag to compare

View all tags
v1.4.13

What's New

What's Changed

  • perf(storage): add cooperative yielding to prevent event loop blocking by @danielaskdd in #2847
  • fix: sanitize entity_type in Memgraph upsert_node to prevent Cypher injection (CWE-89) by @sebastiondev in #2849
  • perf(doc-status): add get_docs_by_statuses to all backends and fix PG pool/pagination bugs by @danielaskdd in #2853
  • Fix setup .env regeneration for preserved custom variables by @danielaskdd in #2854
  • Fix missing file_path in entity merge upserts by @danielaskdd in #2857
  • fix(memgraph): preserve start node in knowledge graph query by @danielaskdd in #2868
  • fix(auth): reject default JWT secret when AUTH_ACCOUNTS is configured by @danielaskdd in #2869
  • fix(postgres): handle quoted AGE entity ids in edge retrieval by @danielaskdd in #2872

New Contributors

Full Changelog: v1.4.12...v1.4.13

Contributors

danielaskdd and sebastiondev
Loading

v1.4.12

27 Mar 05:52
@danielaskdd danielaskdd
v1.4.12
ffd9114

Choose a tag to compare

View all tags
v1.4.12

Hot Fixes

  • Optimize Postgres Vector DB upsert performance by increasing the batch size to 200 records per operation.
  • Resolved issue with opening PDF files protected by permission-only restrictions
  • Fixed pipeline cancellation causing filenames to be incorrectly changed to 'unknown_source'

What's Changed

New Contributors

Full Changelog: v1.4.11...v1.4.12rc1

Contributors

alexbevi, danielaskdd, and Daggle24
Loading

v1.4.11

20 Mar 08:41
@danielaskdd danielaskdd
v1.4.11
6d120e7

Choose a tag to compare

View all tags
v1.4.11

Important Notes

  • Integrated OpenSearch as a unified storage backend, providing comprehensive support for all four LightRAG storage types: KV, Vector, Graph, and DocStatus.
  • Introduced an interactive setup wizard to streamline configuration, replacing manual .env file editing. Support for local deployment of embedding, reranking, and storage backends via Docker Compose is now available. For further details, please refer to Interactive Setup Guide.

What's New

  • Add OpenSearch as unified storage backend by @LantaoJin in #2739
  • Add OpenSearchKVStorage support to LLM cache tools by @danielaskdd in #2790
  • Add Makefile for quick deployment by @mlimarenko in #2548
  • Refactor(Makefile): split monolithic wizard into modular env-base/storage/server targets by @danielaskdd in #2763
  • Add OpenSearch storage configuration support to the interactive setup wizard by @LantaoJin in #2797
  • perf(postgres): optimize KV storage upsert using executemany by @wkpark in #2742

What's Fixed

  • Fix Qdrant large upsert payload failures with bounded batching by @danielaskdd in #2740
  • build(deps): bump the github-actions group with 2 updates by @dependabot[bot] in #2737
  • perf: use deque for BFS queue in get_knowledge_subgraph() by @giulio-leone in #2725
  • perf: batch pre-compute query embeddings to eliminate sequential API round-trips by @errajibadr in #2729
  • fix: reduce FaissVectorDBStorage meta.json file size by excluding vectors by @Br1an67 in #2733
  • Enhance current MilvusVectorDBStorage with parameterized configuration by @hanlianlu in #2672
  • fix: preserve failed-doc chunk metadata for reliable deletion cleanup by @danielaskdd in #2749
  • fix: align zhipu adapter with official thinking and dimensions api by @ChenJiahao1 in #2775
  • fix(operate,utils): correct typos in log messages and remove dead code by @lailoo in #2781
  • perf(opensearch): Remove refresh="wait_for" from OpenSearch storage backends by @LantaoJin in #2786
  • fix(api): sanitize workspace from CLI args and HTTP headers to prevent injection by @danielaskdd in #2792
  • fix(api): normalize missing document file paths by @danielaskdd in #2793
  • fix: prevent None file_path from propagating as unknown_source by @he-yufeng in #2796

New Contributors

Full Changelog: v1.4.10...v1.4.11

Contributors

wkpark, LantaoJin, and 10 other contributors
Loading

v1.4.11rc2

13 Mar 06:19
@danielaskdd danielaskdd
v1.4.11rc2
7d53da4

Choose a tag to compare

View all tags
v1.4.11rc2

What's New

  • Add Makefile for quick deployment by @mlimarenko in #2548
  • Refactor(Makefile): split monolithic wizard into modular env-base/storage/server targets by @danielaskdd in #2763

For detail information about setup wizard, pls refer to: InteractiveSetup.md

What's Changed

  • Fix Qdrant large upsert payload failures with bounded batching by @danielaskdd in #2740
  • perf: use deque for BFS queue in get_knowledge_subgraph() by @giulio-leone in #2725
  • perf: batch pre-compute query embeddings to eliminate sequential API round-trips by @errajibadr in #2729
  • fix: reduce FaissVectorDBStorage meta.json file size by excluding vectors by @Br1an67 in #2733
  • Enhance current MilvusVectorDBStorage with parameterized configuration by @hanlianlu in #2672
  • fix: preserve failed-doc chunk metadata for reliable deletion cleanup by @danielaskdd in #2749
  • build(deps-dev): bump the ui-components group in /lightrag_webui with 2 updates by @dependabot[bot] in #2750
  • build(deps): bump the frontend-minor-patch group in /lightrag_webui with 3 updates by @dependabot[bot] in #2751
  • build(deps): bump the github-actions group with 4 updates by @dependabot[bot] in #2759

New Contributors

Full Changelog: v1.4.10...v1.4.11rc2

Contributors

giulio-leone, hanlianlu, and 5 other contributors
Loading

v1.4.10

27 Feb 07:39
@danielaskdd danielaskdd
v1.4.10
6286eb7
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.4.10

What's New

  • feat: Add POSTGRES_ENABLE_VECTOR option to conditionally disable pgvector extension by @StoreksFeed in #2683
  • Add i18n support for Vietnamese by @zAcherttp in #2708

What's Changed

New Contributors

Full Changelog: v1.4.9.11...v1.4.10

Contributors

Krytos, skogsbaeck, and 10 other contributors
Loading

v1.4.9.11

15 Jan 18:27
@danielaskdd danielaskdd
v1.4.9.11
411b1ce

Choose a tag to compare

View all tags
v1.4.9.11

Hot Fixed

  • Fix OpenAI LLM binding options not loaded from environment variables by @danielaskdd in #2585

What's New

What's Fixed

  • docs: fix the simple program rag init function return value in README.md by @Peefy in #2532
  • docs: fix the simple program rag init function return value in README-zh.md by @Peefy in #2534
  • feat: Implement WebUI Token Auto-Renewal (Sliding Window Expiration) by @danielaskdd in #2543
  • Fixes the Gemini integration example in the README by @vishvaRam in #2537
  • Add Gemini demo for LightRAG by @vishvaRam in #2538
  • Add LightRAG demo with PostgreSQL and Gemini integration by @vishvaRam in #2556
  • Update PostgreSQL demo script reference in README.md by @vishvaRam in #2557
  • Fix: Enhance PostgreSQL Reconnection Tolerance for HA Deployments by @danielaskdd in #2562
  • Add NEO4J_DATABASE variable to README by @vishvaRam in #2578
  • Bump the frontend-minor-patch group in /lightrag_webui with 2 updates by @dependabot[bot] in #2577
  • Add LightRAG demo script with vLLM integration by @vishvaRam in #2582

New Contributors

Full Changelog: v1.4.9.10...v1.4.9.11

Contributors

coldfire-x, Peefy, and 5 other contributors
Loading

v1.4.9.10

23 Dec 01:10
@danielaskdd danielaskdd
v1.4.9.10
8c8186a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.4.9.10

What's Changed

  • Hot Fix AttributeError in Neo4JStorage and MemgraphStorage when using storage specified workspace env var by @danielaskdd in #2526

Full Changelog: v1.4.9.9...v1.4.9.10

Contributors

danielaskdd
Loading

v1.4.9.9

22 Dec 17:49
@danielaskdd danielaskdd
v1.4.9.9
dccf1ef
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.4.9.9

Release Note V1.4.9.9

Important Notes

  • Add Workspace Isolation for Pipeline Status and In-memory Storage: Multiple LightRAG instances with distinct workspaces can be created simultaneously, marking a significant advancement toward seamless workspace switching within a single LightRAG server.

  • Add Workspace Vector Data Isolation by Model Name and Dimension for PostgreSQL and Qdrant: Previously, LightRAG used a single collection/table for difference embedding model and dimension, which caused dimension mismatch crashes or data pollution in multi-workspace.

  • Dimension Selection is Supported for OpenAI and Gemini Embedding model with new env var introduced: EMBEDDING_SEND_DIM

  • Add LLM Cache Migration and LLM Query Cache Cleanup Tools Between Different KV Storage: enabling users to switch storage backends without losing cached extraction and summary data.

  • Enhanced Enhanced DOCX Extraction with Table Content Support.

  • Enhanced XLSX extraction with proper handling of tab and newline characters within cells.

  • Fix Critical Security Vulnerability in React Server Components: #2494

  • Add Automatic Text Truncation Support for Embedding Functions: OpenAI embedding function now respect max_token_size value in EmbeddingFunc, and automatic truncate input text to prevent API errors caused by texts exceeding model token limits.

What's Breaking (for LightRAG Core integration only)

  • Rename params of chunking function: If you incorporate the chunking function into LightRAG and pass parameters by name, corresponding code updates are required.
def chunking_by_token_size(
    tokenizer: Tokenizer,
    content: str,
    split_by_character: str | None = None,
    split_by_character_only: bool = False,
    chunk_overlap_token_size: int = 100,
    chunk_token_size: int = 1200,
) -> list[dict[str, Any]]:
  • Inject an embedding_func with model_name to LightRAG using wrap_embedding_func_with_attrs:
@wrap_embedding_func_with_attrs(
    embedding_dim=1536, max_token_size=8192, model_name="text-embedding-3-small"
)
@retry(
    stop=stop_after_attempt(3),
    wait=wait_exponential(multiplier=1, min=4, max=60),
    retry=(
        retry_if_exception_type(RateLimitError)
        | retry_if_exception_type(APIConnectionError)
        | retry_if_exception_type(APITimeoutError)
    ),
)
async def embedding_func(texts: list[str]) -> np.ndarray:
    client = AzureOpenAI(
        api_key=AZURE_OPENAI_API_KEY,
        api_version=AZURE_EMBEDDING_API_VERSION,
        azure_endpoint=AZURE_OPENAI_ENDPOINT,
    )
    embedding = client.embeddings.create(model=AZURE_EMBEDDING_DEPLOYMENT, input=texts)

    embeddings = [item.embedding for item in embedding.data]
    return np.array(embeddings)

rag = LightRAG(
      working_dir=WORKING_DIR,
      llm_model_func=llm_model_func,
      embedding_func=embedding_func,
)

To ensure seamless transition, legacy code injecting embedding_func without model_name will continue to interface with the original non-suffixed vector tables.

What's New

  • Feat: Add Chain of Thought Support for Gemini LLM by @danielaskdd in #2326

  • Feat: Add Optional Embedding Dimension Control with OpenAI API by @danielaskdd in #2328

  • Feat: Add Gemini Embedding Support to LightRAG by @danielaskdd in #2329

  • Feat: Add LLM Cache Migration Tool by @danielaskdd in #2330

  • Feat: Add LLM Query Cache Cleanup Tool by @danielaskdd in #2335

  • Support async chunking func to improve processing performance when a heavy chunking_func is passed in by user by @tongda in #2336

  • Add ollama cloud support by @LacombeLouis in #2348

  • Feat: Add Workspace Isolation for Pipeline Status and In-memory Storage by @danielaskdd in #2369

  • feat: add vchordrq vector index support for PostgreSQL by @wmsnp in #2378

  • Feat: Enhanced DOCX Extraction with Table Content Support by @danielaskdd in #2383

  • Feat: Enhance XLSX Extraction by Adding Separators and Escape Special Characters by @danielaskdd in #2386

  • Optimize for OpenAI Prompt Caching: Restructure entity extraction pro… by @Ghazi-raad in #2426

  • feat: Vector Storage Model Isolation with Automatic Migration by @BukeLy in #2391

  • feat: Implement Vector Database Model Isolation and Auto-Migration by @danielaskdd in #2513

  • feat: Add Automatic Text Truncation Support for Embedding Functions by @danielaskdd in #2523

What's Changed

  • Fix: Remove Duplicate Entity/Realtion Tracking Deletion in adelete_by_doc_id by @danielaskdd in #2322

  • Fix spelling errors in the "使用PostgreSQL存储" section of README-zh.md by @huangbhan in #2327

  • Add dimensions parameter support to openai_embed() by @yrangana in #2323

  • Fix Gemini driver retry mechanism by @danielaskdd in #2331

  • HotFix: Restore OpenAI Streaming Response & Refactor keyword_extraction Parameter by @danielaskdd in #2334

  • Refactor: Migrate PDF processing dependency from pypdf2 to actively pypdf by @danielaskdd in #2338

  • Fix: Prevent UnicodeEncodeError in JSON storage operations by @danielaskdd in #2344

  • Remove deprecated response_type parameter from query settings UI by @danielaskdd in #2345

  • Refactor: Optimize write_json for Memory Efficiency and Performance by @danielaskdd in #2346

  • Refact: Remove blocking dependency installation from document upload handlers by @danielaskdd in #2350

  • Refact: Implement Lazy Configuration Initialization for API Server by @danielaskdd in #2351

  • Refact: Enhance DOCLING integration with lazy loading and macOS safeguards by @danielaskdd in #2352

  • Fix: Robust error handling for async database operations in graph storage by @danielaskdd in #2356

  • Update the value corresponding to the extracted entity relationship keywords by @sleeepyin in #2358

  • Add macOS fork safety check for Gunicorn multi-worker mode by @danielaskdd in #2360

  • Refact: Add Embedding Token Limit Configuration and Improve Error Handling by @danielaskdd in #2359

  • Refact: Add Embedding Dimension Validation in EmbeddingFunc by @danielaskdd in #2368

  • test: Convert test_workspace_isolation.py to pytest style by @BukeLy in #2371

  • refactor(chunking): rename params and improve docstring for chunking by @EightyOliveira in #2379

  • Fix: Add chunk token limit validation with detailed error reporting by @danielaskdd in #2389

  • Fix: Remove redundant exception logging to eliminate pytest shutdown errors by @danielaskdd in #2390

  • issue-2394: use deployment variable instead of model for embeddings API call by @Amrit75 in #2395

  • Refactor: Centralize keyword_extraction parameter handling in OpenAI LLM implementations by @danielaskdd in #2401

  • Refact: Consolidate Azure OpenAI and OpenAI implementations by @danielaskdd in #2403

  • Update README.md by @chaohuang-ai in #2408

  • Update README.md by @chaohuang-ai in #2409

  • feat: create copilot-setup-steps.yml by @netbrah in #2410

  • Fix: Add Comprehensive Retry Mechanism for Neo4j Storage Operations by @danielaskdd in #2417

  • Refact: Allow API Server to Start Without Built WebUI Assets by @danielaskdd in #2418

  • fix:exception handling order error by @EightyOliveira in #2421

  • Doc: Update README examples to prevent double-wrapping of embedding functions by @danielaskdd in #2432

  • Fix: Add configurable model support for Jina embedding by @danielaskdd in #2433

  • Fix typos discovered by codespell by @cclauss in #2434

  • Update README.md by @chaohuang-ai in #2439

  • Fix KaTeX chemistry formula rendering (\ce command) not working by @danielaskdd in #2443

  • fix(postgres): Add CASCADE to AGE extension creation for automatic dependency resolution by @danielaskdd in #2446

  • Add Python 3.13 and 3.14 to the testing by @cclauss in #2436

  • Keep GitHub Actions up to date with GitHub's Dependabot by @cclauss in #2435

  • chore: optimize Dependabot configuration with dependency grouping and PR limits by @danielaskdd in #2447
    ...

Read more

Contributors

mccahill, tongda, and 15 other contributors
Loading

v1.4.9.8

06 Nov 13:51
@danielaskdd danielaskdd
v1.4.9.8
5bcd292

Choose a tag to compare

View all tags
v1.4.9.8

What's New

What's Changed

  • Refact: Auto-refresh of Popular Labels When Pipeline Completes by @danielaskdd in #2291
  • Fix empty context validation bug and improve naming consistency in query context building by @danielaskdd in #2295
  • Refact: Enhanced RAG Evaluation CLI with Two-Stage Pipeline and Improved UX by @danielaskdd in #2311
  • Refact: Separate Configuration of RAGAS for LLM and Embeddings by @danielaskdd in #2314
  • Refactor: Remove Deprecated Chunk-Based Query Methods and Improve Graph Unit Test by @danielaskdd in #2319
  • Fix node retrieval fail with special characters in IDs for Postgres AGE GraphStorage by @danielaskdd in #2320
  • Fix performance bottleneck in document deletion by @danielaskdd in #2321

New Contributors

Full Changelog: v1.4.9.7...v1.4.9.8

Contributors

danielaskdd, Humphryshikunzi, and anouar-bm
Loading